© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13609
    Prev
    Next
    INDEX
    Explanations

    Romeo and Juliet

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eucalyptus
    0.64
     eucalyptus
    0.61
     Tark
    0.61
    狍
    0.59
     معاد
    0.58
     Curl
    0.57
     JavaBean
    0.56
     Steen
    0.55
     Lehmann
    0.55
    飯
    0.55
    POSITIVE LOGITS
     Romeo
    2.09
    Romeo
    2.03
     Juliet
    1.97
    Shakespeare
    1.29
     juli
    1.28
     Shakespeare
    1.27
    Jul
    1.24
     Verona
    1.23
     Juli
    1.22
     Juliette
    1.22
    Activations Density 0.013%

    No Known Activations